more readme

README.md

@@ -9,4 +9,46 @@ datasets:
 
 Fine-tune of Upstage AI's SOLAR-10.7B-Instruct-v1.0 model, using the OpenHermes, Platypus, and Capybara datasets.
 
-Fine-tuned on 8x4090s for 1.25 epochs.
+Fine-tuned on 8x4090s for 1.25 epochs.
+
+
+### Model Sources [optional]
+
+- **Repository:** TBD
+- **Demo:** TBD
+
+## Bias, Risks, and Limitations
+
+This fine-tune has had zero alignment, safety data, or anything else shoved down it's throat.
+
+## Training Details
+
+### Training Data
+
+See the sidebar for links to the relevant datasets.
+
+### Training Procedure 
+
+Trained 
+
+## Evaluation
+
+TBD
+
+## Training procedure
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Framework versions
+
+- PEFT 0.6.0